提出可分级控制的图像生成方法，提升视觉自回归模型的可控性与质量。
SCALAR: Scale-wise Controllable Visual Autoregressive Learning
- 按层级注入语义控制信号，实现生成过程中的持续引导。
- 在多任务上生成质量与控制精度均优于现有方法。
- 支持多种控制模态统一建模，适合需要灵活调控的应用场景。
可控图像生成已成为视觉生成建模的关键方向，但视觉自回归（VAR）模型因其分层逐尺度预测机制，面临控制编码低效和干扰性注入的问题。本文提出SCALAR，一种基于VAR的可控生成方法，引入新型分尺度条件解码机制。利用预训练图像编码器提取语义控制信号编码，并投影为特定尺度的表示，注入到VAR主干对应层中，实现生成全过程的稳定、结构对齐引导。在此基础上，构建SCALAR-Uni，将多种控制模态映射至共享潜空间，实现单模型下多条件灵活引导。大量实验表明，SCALAR在多个任务中均取得更优的生成质量与控制精度。代码已开源：https://github.com/AMAP-ML/SCALAR。
原文摘要 · Abstract (English)
Controllable image synthesis, which enables fine-grained control over generated outputs, has emerged as a key focus in visual generative modeling. However, controllable generation remains challenging for Visual Autoregressive (VAR) models due to their hierarchical, next-scale prediction style. Existing VAR-based methods often suffer from inefficient control encoding and disruptive injection mechanisms that compromise both fidelity and efficiency. In this work, we present SCALAR, a controllable generation method based on VAR, incorporating a novel Scale-wise Conditional Decoding mechanism. SCALAR leverages a pretrained image encoder to extract semantic control signal encodings, which are projected into scale-specific representations and injected into the corresponding layers of the VAR backbone. This design provides persistent and structurally aligned guidance throughout the generation process. Building on SCALAR, we develop SCALAR-Uni, a unified extension that aligns multiple control modalities into a shared latent space, supporting flexible multi-conditional guidance in a single model. Extensive experiments show that SCALAR achieves superior generation quality and control precision across various tasks. The code is released at https://github.com/AMAP-ML/SCALAR.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。